fix: use freemodel as default cora provider#254
Merged
Conversation
…elope Adds Sentry protocol types for Phase 1 transaction support: - SpanStatus enum (16 variants, serde snake_case) - Span struct (op, trace_id, parent_span_id, timing, tags, data) - Transaction struct (event_id, name, spans, release, env, contexts) - ParsedEnvelope struct (events + transactions, extensible for Phase 2-3) All fields use skip_serializing_if for minimal wire size. 12 new unit tests covering serde round-trips and ParsedEnvelope usage. Closes #235
Switch from LiteLLM proxy (localhost:4000) to freemodel (gpt-5.4 via api.freemodel.dev). The LiteLLM proxy is not available in all environments (CI, agent containers). - model: glm-5.1 → gpt-5.4 - base_url: http://localhost:4000 → https://api.freemodel.dev/v1
Fix Cargo Audit failure: remote memory exhaustion in quinn-proto from unbounded out-of-order stream reassembly. Severity: 7.5 (high). Dependency chain: trapfalld → reqwest → quinn → quinn-proto (quinn-proto only resolved on non-linux targets).
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
.cora.yamlpointed to LiteLLM proxy (http://localhost:4000) which is not available in CI/agent containers. Cora review would fail silently.Fix
glm-5.1→gpt-5.4(freemodel)http://localhost:4000→https://api.freemodel.dev/v1API key still comes from
CORA_API_KEYenv var (injected by Hermes from.env).Verification
Cora pre-commit hook ran on commit — passed.